Title :
Lazy yet efficient land-cover map generation for HR optical images
Author :
Michel, J. ; Malik, J. ; Inglada, J.
Author_Institution :
C-S-IGI, Toulouse, France
Abstract :
High resolution optical remote sensing images allow to produce accurate land-cover maps. This is usually achieved using an ad-hoc mixture of image segmentation and supervised classification. The main drawback of this approach is that it does not scale for real world complete scenes. In this paper we present a framework which allows to implement this kind of image analysis without scale issues.
Keywords :
geophysical image processing; image classification; image segmentation; terrain mapping; HR optical image; image segmentation; land cover map generation; remote sensing; supervised classification; Context; Image analysis; Image segmentation; Pixel; Remote sensing; Support vector machines; Training; Geographical databases; Land-cover maps; Object-based image analysis;
Conference_Titel :
Geoscience and Remote Sensing Symposium (IGARSS), 2010 IEEE International
Conference_Location :
Honolulu, HI
Print_ISBN :
978-1-4244-9565-8
Electronic_ISBN :
2153-6996
DOI :
10.1109/IGARSS.2010.5653286
